Monmouth says Hillary has a 13% lead. This poll is major league amateur hour
The 803 people sampled were pulled from two different datasets. The criteria is clearly they wanted 1/2 landlines and 1/2 Cell Phones, rather than the actual number.
With 803 sample of 142 million people, small judgement errors get magnified enormously. The survey “adjusted” for non representative sampling in party identification, sex, age and race. The weighting doesn’t adjust for things like section of the country, rural vs urban, unemployed (more likely to be reached by phone), number of children, marital status, income… The poll weighted on those attributes they considered significant.
The poll assumes 47% of the population is men. They actually got 51% men. The survey assumes that 25% of registered voters should be aged 18-34. What they actually got was 15%. Weighting is to some degree necessary, but the larger the deviation between the population and the sample, the less reliable the sample is. With 803 people, that means only 59 were women under 35. Their model predicted 106 women should have been under 35, so they needed to weigh those women almost 2:1… Since there are 4 weighting factors, all 4 have to be combined – not by addition or multiplication. In the under 35 women, what percentage are Republicans and how many did they get? Does the weighting apply equally on every question? If a black woman under 35 woman is weighted 2.5:1, and you ask her if she thinks president Obama is doing a good job as president, we already know that 86% of her sample will say yes, so 200% of all under 35 black women support Obama. See the problem?
The solution is to fix the sample, not to weight it after the fact.
Here is an interesting thought – if you know that polls are completely wrong (and they are) then what is the accurate barometer of voter opinion? Let’s open our minds to the thought that Facebook and Twitter carry the true pulse of the election campaign. Counting up “likes” and “follows”, Hillary is in some difficulty if this is a valid method.
The problem I always see with these polls is that busy adults who work, pay their bills on time, and support families don’t answer phone calls from unknown numbers. Thus automatically the poll has eliminated the conservative base of the Republican party. All other demographic breakouts are secondary to the fact that productive people are very hard to contact for a poll!
They try to fudge that with weighting the sample to “true it up”, but the problem is their variables for doing the reweighting are very arbitrary. Cell Phones are also totally disrupting things. I’ve never paid for caller ID on a landline, but it is automatic on the cell phone.
There are also lots of intrinsic problems that people are not going to own up to. If the pollster is using live surveyors, they can inadvertently inject bias. Small voice inflections can influence what people say. Is the caller female? Sounds gay? Black? Hispanic? Do they assign callers based on the ethno-demographics of the person called. Are they accounting that many cell phone users never change their area code when they move?
This ^ What prboylan said. ‘The silent majority’.
Hilliary don’t know cheit. If you are on the government dole, in your section 8 housing and have their obo phones, NBC, CNN and CBS who call and make these crazy polls, get the caller list from the social services offices.
If they spoke to real Americans out here in flyover country, they would find out no one believes the crap hilliary is shoveling. She is not for women or kids. Oh hell no, she is for abortion and billy clinky flying on planes to the Bahamas with underage runaway girls.
Obo just watches sports center 7 hours a day , hell he doesn’t do anything. Who in their right mind votes for this type of circus ?
parrott
At least in the primary, the exit polls said – older single women with college degrees and blacks (except some young black men who liked Sanders)